Abstract: A computer-implemented method, system and computer program product for training a machine learning model using noisily labeled data. A classification model is built in which a classified dataset is inputted, where the classified dataset includes label noise. Based on the input, the classification model generates a prediction of class probabilities. Furthermore, a second model is built with the same architecture as the classification model, where the second model is a moving average of the classification model, and where the second model generates a prediction of class probabilities. Weight factors used to weight such predictions of these models are generated by the artificial neural network (ANN), in which the weighted predictions are used by the ANN to obtain a prediction of class probabilities. The predictions of class probabilities of the ANN and the classification model are then combined to train the machine learning model.

Abstract: A computer-implemented method, system and computer program product for processing data. Data, including single data points (e.g., images) or entire sequences of data (e.g., speech, video), is received to be processed. A long short term memory structure is utilized to process the received data, where the long short term memory structure includes hidden state sharing modules for allowing information sharing in hidden states across different tasks. The hidden state sharing modules include broadcast modules which are configured to send hidden states of the current task to all previous modules and collect modules which are configured to collect all the hidden states from all the previous modules. In this manner, catastrophic forgetting is avoided by preventing the loss of previously learned information via the use of hidden state sharing modules.

Abstract: A method, a computer program product, and a computer system fuse features for multi-modal classifications for a plurality of modality inputs. The method includes receiving a request indicative of the modality inputs to be selected. The method includes performing an embeddings level fusion operation to concatenate features from the modality inputs. The method includes performing a multi-modal discriminative feature level fusion operation that integrates feature representations learned by applying different network structures on the modality inputs. The method includes determining weights of the concatenated features and the feature representations based on a measure of the concatenated features and the feature representations indicative of affecting a final prediction performance. The method includes generating fused features for the modality inputs based on the concatenated features, the feature representations, and the weights.

Abstract: A method, a computer system, and a computer program product for using distinct paths with cross connections for distinct tasks to prevent catastrophic forgetting in class-incremental scenarios. Embodiments of the present invention may include receiving one or more tasks sequentially. Embodiments of the present invention may include applying one or more shareable blocks to the one or more tasks. Embodiments of the present invention may include learning one or more distinct paths for the one or more tasks. Embodiments of the present invention may include adding one or more cross connections between the one or more tasks. Embodiments of the present invention may include adding an aggregation block to collect one or more outputs from the distinct paths of each of the one or more tasks. Embodiments of the present invention may include providing a prediction.

Abstract: A method of generating application program interface (API) mashups is provided. The method may include grouping a plurality of APIs into a plurality of sub-clusters based on at least one keyword for each API of the plurality of APIs. The method may also include identifying a plurality of keyword combinations for the plurality of sub-clusters based on real-world data and two or more keywords for the plurality of sub-clusters. Further, the method may include determining a plurality of possible API mashups including two or more APIs of the plurality of APIs for the plurality of keyword combinations. The method may also include processing the plurality of possible API mashups to generate at least one prioritized API mashup of the plurality of possible API mashups, the at least one prioritized API mashup associated with at least one keyword combination of the plurality of keyword combinations.

Abstract: A method of generating application program interface (API) mashups is provided. The method may include grouping a plurality of APIs into a plurality of sub-clusters based on at least one keyword for each of the plurality of APIs. The method may also include identifying at least one keyword combination for the one or more sub-clusters based on real-world data and two or more keywords for the plurality of sub-clusters. Further, the method may include determining one or more possible API mashups including two or more APIs of the plurality of APIs for the at least one keyword combination. In addition, the method may include determining a similarity score for each possible API mashup of the one or more possible API mashups. The method may also include identifying at least one API mashups from the one or more possible mashups based on the similarity score for each possible API mashup.

Abstract: A method of generating application program interface (API) mashups is provided. The method may include grouping a plurality of APIs into a plurality of sub-clusters based on at least one keyword for each of the plurality of APIs. The method may also include identifying at least one keyword combination for the one or more sub-clusters based on real-world data and two or more keywords for the plurality of sub-clusters. Further, the method may include determining one or more possible API mashups including two or more APIs of the plurality of APIs for the at least one keyword combination. In addition, the method may include determining a similarity score for each possible API mashup of the one or more possible API mashups. The method may also include identifying at least one API mashups from the one or more possible mashups based on the similarity score for each possible API mashup.

Abstract: A method of generating application program interface (API) mashups is provided. The method may include grouping a plurality of APIs into a plurality of sub-clusters based on at least one keyword for each API of the plurality of APIs. The method may also include identifying a plurality of keyword combinations for the plurality of sub-clusters based on real-world data and two or more keywords for the plurality of sub-clusters. Further, the method may include determining a plurality of possible API mashups including two or more APIs of the plurality of APIs for the plurality of keyword combinations. The method may also include processing the plurality of possible API mashups to generate at least one prioritized API mashup of the plurality of possible API mashups, the at least one prioritized API mashup associated with at least one keyword combination of the plurality of keyword combinations.